Official Code for AdvRush: Searching for Adversarially Robust Neural Architectures (ICCV '21)

Last update: Dec 10, 2022

Related tags

Overview

AdvRush

Official Code for AdvRush: Searching for Adversarially Robust Neural Architectures (ICCV '21)

Environmental Set-up

Python == 3.6.12, PyTorch == 1.2.0, torchvision == 0.4.0

AdvRush Search Process

cd advrush && python train_search.py --batch_size 32 --gpu 0 --epochs 60 --a_gamma 0.01 --a_warmup_epochs 0 --w_warmup_epochs 60 --loss_hessian loss_cure

Adversarial Training

cd advrush && python adv_train.py --batch_size 64 --gpu 0 --epochs 200 --adv_loss pgd --arch ADVRUSH

Evaluation under PGD Attack

Prior to the evaluation process, add all necessary checkpoint files (preferably in the form of .pth.tar) to the /eval/checkpoints folder. To conduct white-box attacks,

cd eval &&
python pgd_attack.py --white-box-attack True --test-batch-size 10 --arch [arch_name] --checkpoint [./checkpoints/file_name.pth.tar] --data_type [cifar10/svhn]

To conduct black-box attacks,

cd eval &&
python pgd_attack.py --test-batch-size 10 --target_arch [target_arch] --target_checkpoint [./checkpoints/target_file.pth.tar] --source_arch [source_arch] --source_checkpoint [./checkpoints/source_file.pth.tar] --data_type cifar10

References

DARTS: Differentiable Architecture Search [ICLR '19] code paper

Robustness via Curvature Regularization, and Vice Versa [CVPR '19] code paper

Tradeoff-inspired Adversarial Defense via Surrogate-loss Minimization [ICML '19] code paper

Official Code for AdvRush: Searching for Adversarially Robust Neural Architectures (ICCV '21)

Related tags

Overview

AdvRush

Environmental Set-up

AdvRush Search Process

Adversarial Training

Evaluation under PGD Attack

References

Owner

Learn the Deep Learning for Computer Vision in three steps: theory from base to SotA, code in PyTorch, and space-repetition with Anki

Code of paper: "DropAttack: A Masked Weight Adversarial Training Method to Improve Generalization of Neural Networks"

The official codes of "Semi-supervised Models are Strong Unsupervised Domain Adaptation Learners".

[NIPS 2021] UOTA: Improving Self-supervised Learning with Automated Unsupervised Outlier Arbitration.

TensorFlow implementation of Elastic Weight Consolidation

ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation

coldcuts is an R package to automatically generate and plot segmentation drawings in R

Point-NeRF: Point-based Neural Radiance Fields

This repo generates the training data and the model for Morpheus-Deblend

Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields.

Cockpit is a visual and statistical debugger specifically designed for deep learning.

Deep Learning for 3D Point Clouds: A Survey (IEEE TPAMI, 2020)

Out-of-distribution detection using the pNML regret. NeurIPS2021

PConv-Keras - Unofficial implementation of "Image Inpainting for Irregular Holes Using Partial Convolutions". Try at: www.fixmyphoto.ai

PyTorch implementation of Progressive Growing of GANs for Improved Quality, Stability, and Variation.

face property detection pytorch

This repository accompanies the ACM TOIS paper "What can I cook with these ingredients?" - Understanding cooking-related information needs in conversational search

Simply enable or disable your Nvidia dGPU

XtremeDistil framework for distilling/compressing massive multilingual neural network models to tiny and efficient models for AI at scale

Permute Me Softly: Learning Soft Permutations for Graph Representations